Artificial neural networks (Anns) for density and viscosity predictions of CO2 loaded alkanolamine + H2O mixtures

Abstract

The physical properties, like density and viscosity, of alkanolamine + H2O (water) + CO2 (carbon dioxide) mixtures receive a significant amount of attention as they are essential in equipment sizing, mathematical modelling and simulations of amine-based post-combustion CO2 capture processes. Non-linear models based on artificial neural networks (ANNs) were trained to correlate measured densities and viscosities of monoethanol amine (MEA) + H2O, MEA + H2O + CO2, and 2-amino-2-methyl-1-propanol (AMP) + MEA + H2O + CO2 mixtures and results were compared with conventional correlations found in literature. For CO2-loaded aqueous amine mixtures, results from the ANN models are in good agreement with measured properties with less than 1% average absolute relative deviation (AARD). The ANN-based methodology shows much better agreement (R2 > 0.99) between calculated and measured values than conventional correlations.